对象检测收件箱。14个对象检测指标:平均平均精度(mAP)、平均召回率(AR)、时空管平均精度(STT-AP)。该项目支持不同的边界框格式,例如COCO、PascAL、Imagenet等。
coco-dataset 开源项目推荐(210 个)
coco-dataset 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 210 个仓库An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come
(Pretrained weights provided) EfficientDet: Scalable and Efficient Object Detection implementation by Signatrix GmbH
Multi-person Human Pose Estimation with HRNet in Pytorch
Distribution-Aware Coordinate Representation for Human Pose Estimation
[CVPR 2021] VirTex: Learning Visual Representations from Textual Annotations
Implementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models
将COCO注释(CVAT)转换为YOLO-seg(实例分段)和YOLO-obb(定向边界盒检测)的注释
Localize and identify multiple objects in a single image.
a subset of coco dataset for faster experimentation
How to create custom COCO data set for object detection
Convert segmentation RGB mask images to COCO JSON format
如何创建自定义COCO数据集用于实例分割
[ECCV-20] Official PyTorch implementation of HoughNet, a voting-based object detector.
Keras-tensorflow implementation of PersonLab (https://arxiv.org/abs/1803.08225)
Multi-person Human Pose Estimation with HigherHRNet in Pytorch, with TensorRT support
Pytorch implementation of "AutoAssign: Differentiable Label Assignment for Dense Object Detection"
Chainer implementation of Pose Proposal Networks
Convert VOC format XMLs to COCO format json
[ICCV 2023] - Composed Image Retrieval on Common Objects in context (CIRCO) dataset
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/coco-dataset。
- 该话题在 GitHub 上共有 210 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 7420 Star,覆盖 3 种主要语言,数据更新于 2026-11-09。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。